← All Providers
Fireworks AI
High-performance inference platform optimized for speed and throughput. Offers access to Mixtral, Llama, Qwen, DeepSeek, and Fireworks' own Mixtral variants with industry-leading speed.
Visit Fireworks AI →Plans & Pricing
Free Tier
$0- ✓Limited daily tokens
- ✓Access to Mixtral and Llama models
Pro
From $0.20/1M tokens- ✓Mixtral 8x22B: $0.20/1M in / $0.60/1M out
- ✓Llama 3.1 70B: $0.65/1M in / $0.65/1M out
- ✓Qwen3 32B: $0.30/1M in / $0.90/1M out
- ✓Very fast inference
Free Tier
Free: $1 in starter credits. Rate-limited free tier for testing. Paid: from $0.20/1M tokens.
Models (4)
Compare →| Model | Context | In /1M | Out /1M | Capabilities |
|---|---|---|---|---|
Mixtral 8x22B (Fireworks) ChatFunctions | 128K | $0.20 | $0.60 | ChatFunctionsStreaming |
Llama 3.1 70B (Fireworks) ChatFunctions | 128K | $0.65 | $0.65 | ChatFunctionsStreaming |
Qwen3 32B (Fireworks) ChatFunctions | 131K | $0.30 | $0.90 | ChatFunctionsStreaming |
DeepSeek V3.2 (Fireworks) ChatFunctions | 128K | $0.50 | $0.90 | ChatFunctionsStreaming |